© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 9504
    Prev
    Next
    INDEX
    Explanations

    phrases related to film and television production processes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Production" or its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sol
    -0.72
     scapego
    -0.69
     center
    -0.68
     Cantor
    -0.67
     antip
    -0.66
    ctl
    -0.66
     champions
    -0.66
     trail
    -0.66
     aisle
    -0.65
     bindings
    -0.65
    POSITIVE LOGITS
     Production
    3.21
    Production
    2.55
    Produ
    2.04
     Produ
    1.98
     Productions
    1.92
     Producer
    1.71
    production
    1.65
    produ
    1.42
     PRODUCT
    1.33
     Prototype
    1.29
    Activations Density 0.022%

    No Known Activations